Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Aleksacom/claude-code-orchestration-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/aleksacom/claude-code-orchestration-agents/change)<a href="https://agentmods.dev/commands/aleksacom/claude-code-orchestration-agents/change"><img src="https://agentmods.dev/badge/commands/aleksacom/claude-code-orchestration-agents/change/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/aleksacom/claude-code-orchestration-agents/change"><img src="https://agentmods.dev/badge/commands/aleksacom/claude-code-orchestration-agents/change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.01673 |
| Opus 5.5 | $0.00017 | $0.00669 |
| Sonnet 5.5 | $0.00008 | $0.00335 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
change scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/change — Universal change orchestrator
Use this command for any work request: feature additions, bug fixes, refactors, renames, doc updates, schema changes, configuration edits.
What this command does
/change <user request> triggers the full planner-routing pipeline:
user request
→ cm-planner (architectural authority — plans, surfaces ratifications)
→ [if STOP_FOR_HUMAN: wait for user decision]
→ executor (Edit, Write, Bash — implements per cm-planner's prompt)
→ git add (stage changes)
→ reviewer (review staged diff — HIGH/MEDIUM/LOW findings)
→ [if BLOCK COMMIT: address findings, re-stage, re-review]
→ conventions-audit (if docs/decisions/** touched OR sub-phase closing)
→ [if BLOCK CLOSURE: address findings or surface override block to user]
→ test-author (if monitored source paths added new behavior)
→ [if TESTS ADDED with failures: fix source bug in separate loop]
→ git commit
→ (loop back to executor if cm-planner prompt has more steps)
→ (when all done) cm-planner in "review commits for push" mode
→ [if BLOCK PUSH: amend / rebase flagged commits]
→ git push
Trigger paraphrases
This command activates on ANY of:
/change <request>(explicit)- "implement X" / "add X" / "fix X" / "refactor X" / "rename X"
- "update the docs to X"
- "change how X works"
- "modify X"
- "remove X" / "delete X"
If user just asks a question without requesting work (e.g., "how does X work?", "what does this do?"), still run through cm-planner for routing — most questions still need planner involvement for the "lookup" workflow.
Pipeline rules
Rule 1 — Planner first, ALWAYS
Before responding to ANY user request in this repository, invoke cm-planner.
Exceptions:
- Direct Claude Code meta-commands (
/agents,/hooks,/plugin) - Pure conversational messages (greetings, acknowledgments)
For every other category — including one-line edits, lookups, and "what does X do" — go through cm-planner.
Rule 2 — STOP_FOR_HUMAN is verbatim
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 186 lines · 42 tokens per session scan A 26040b0d2893
change is a command published in the GitHub repository Aleksacom/claude-code-orchestration-agents (2 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,673 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
worktree
Create a git worktree for isolated feature/fix work.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
resume-project
Run resume-project now — Now / Blocked / Next. Not a cheat sheet.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.